Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1399 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.6429. Min Range: -3.6429
Max Act: 3.6429. Min Act: -0.1700
Data Index: 5741791 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6429. Min Range: -3.6429
Max Act: 3.6429. Min Act: -0.1700
Data Index: 376616 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6429. Min Range: -3.6429
Max Act: 3.5960. Min Act: -0.1700
Data Index: 2869932 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6429. Min Range: -3.6429
Max Act: 3.5803. Min Act: -0.1700
Data Index: 8264513 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6429. Min Range: -3.6429
Max Act: 3.5803. Min Act: -0.1700
Data Index: 6988613 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6429. Min Range: -3.6429
Max Act: 3.5490. Min Act: -0.1700
Data Index: 1884966 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6429. Min Range: -3.6429
Max Act: 3.5490. Min Act: -0.1700
Data Index: 3114738 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6429. Min Range: -3.6429
Max Act: 3.5021. Min Act: -0.1700
Data Index: 8488482 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6429. Min Range: -3.6429
Max Act: 3.5334. Min Act: -0.1700
Data Index: 5183773 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6429. Min Range: -3.6429
Max Act: 3.4551. Min Act: -0.1700
Data Index: 8076796 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6429. Min Range: -3.6429
Max Act: 3.5334. Min Act: -0.1700
Data Index: 3738469 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6429. Min Range: -3.6429
Max Act: 3.5334. Min Act: -0.1700
Data Index: 4265338 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6429. Min Range: -3.6429
Max Act: 3.5334. Min Act: -0.1700
Data Index: 2809696 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6429. Min Range: -3.6429
Max Act: 3.5177. Min Act: -0.1700
Data Index: 1880972 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6429. Min Range: -3.6429
Max Act: 3.5334. Min Act: -0.1700
Data Index: 3406447 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6429. Min Range: -3.6429
Max Act: 3.5177. Min Act: -0.1700
Data Index: 5495877 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6429. Min Range: -3.6429
Max Act: 3.5334. Min Act: -0.1700
Data Index: 5682529 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6429. Min Range: -3.6429
Max Act: 3.4864. Min Act: -0.1700
Data Index: 1248452 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6429. Min Range: -3.6429
Max Act: 3.5334. Min Act: -0.1700
Data Index: 1322138 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6429. Min Range: -3.6429
Max Act: 3.4864. Min Act: -0.1700
Data Index: 302701 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #19